Intelligent Parkinson Disease Prediction Using Machine Learning Algorithms

摘要: Diagnosis of the Parkinson disease through machine learning approache provides better understanding from PD dataset in the present decade. Orange v2. 0b and weka v3. 4.10 has been used in the present experimentation for the statistical analysis, classification, Evaluation and unsupervised learning methods. Voice dataset for Parkinson disease has been retrieved from UCI Machine learning repository from Center for Machine Learning and Intelligent Systems. The dataset contains name, MDVP: Fo (Hz), MDVP: Fhi (Hz), MDVP: Flo (Hz), MDVP: Jitter (%), MDVP: Jitter (Abs), MDVP: RAP, MDVP: PPQ, Jitter: DDP, MDVP: Shimmer, MDVP: Shimmer (dB), Shimmer: APQ3, Shimmer: APQ5, MDVP: APQ, Shimmer: DDA, NHR, HNR, status, RPDE, DFA, spread1, spread2, D2, PPE attributes. The parallel coordinates shows higher variation in Parkinson disease dataset. SVM has shown good accuracy (88.9%) compared to Majority and k-NN algorithms. Classification algorithm like Random Forest has shown good accuracy (90.26) and Naïve Bayes has shown least accuracy (69.23. Higher number of clusters in healthy dataset in Fo and less number in diseased data has been predicted by Hierarchal clustering and SOM.